HIERARCHICAL CLUSTERED OUTLIER DETECTION IN LASER SCANNER POINT CLOUDS

Cleaning laser scanner point clouds from erroneous measurements (outliers) is one of the most time consuming tasks that has to be done before modeling. There are algorithms for outlier detection in different applications that provide automation to some extent but most of the algorithms either are not suited to be used in arbitrary 3 dimensional data sets or they deal only with single outliers or small scale clusters. Nevertheless dense point clouds measured by laser scanners may contain surface discontinuities, noise and diffrent local densities due to the object geometry and the distance of the object to the scanner; Consequently the scale of outliers may vary and they may appear as single or clusters. In this paper we have proposed a clustering algorithm that approaches in two steps with the minimum user interaction and input parameters while it can cop with different scale outliers. In the first step the algorithm deals with large outliers (those which are very far away from main clusters) and the second step cops with small scale outliers. Since the algorithm is based on clustering and uses both geometry and topology of the points it can detect outlier clusters in addition to single ones. We have evaluated the algorithm on a simulated data and have shown the result on some real terrestrial point clouds. The results explain the potential of the approach to cop with arbitrary point clouds and different scale erroneous measurements.

[1]  R. Sokal,et al.  A New Statistical Approach to Geographic Variation Analysis , 1969 .

[2]  Raymond T. Ng,et al.  Distance-based outliers: algorithms and applications , 2000, The VLDB Journal.

[3]  Peter J. Rousseeuw,et al.  Robust Regression and Outlier Detection , 2005, Wiley Series in Probability and Statistics.

[4]  Anil K. Jain,et al.  Data clustering: a review , 1999, CSUR.

[5]  Hans-Peter Kriegel,et al.  LOF: identifying density-based local outliers , 2000, SIGMOD '00.

[6]  Remco C. Veltkamp,et al.  Closed Object Boundaries from Scattered Points , 1994, Lecture Notes in Computer Science.

[7]  Vic Barnett,et al.  Outliers in Statistical Data , 1980 .

[8]  Marco Attene,et al.  Automatic Surface Reconstruction from Point Sets in Space , 2000, Comput. Graph. Forum.

[9]  Joachim Giesen,et al.  New techniques for topologically correct surface reconstruction , 2000, Proceedings Visualization 2000. VIS 2000 (Cat. No.00CH37145).

[10]  Douglas M. Hawkins.  Identification of Outliers , 1980, Monographs on Applied Probability and Statistics.

[11]  Theodore Johnson,et al.  Fast Computation of 2-Dimensional Depth Contours , 1998, KDD.

[12]  Charles T. Zahn,et al.  and Describing GestaltClusters , 1971 .

[13]  G. Sithole,et al.  Segmentation and classification of airborne laser scanner data , 2005 .

[14]  S. Sotoodeh.  OUTLIER DETECTION IN LASER SCANNER POINT CLOUDS , 2006 .

[15]  Edward J. Krakiwsky,et al.  Geodesy, the concepts , 1982 .

[16]  Michaël Aupetit.  High-dimensional labeled data analysis with Gabriel graphs , 2003, ESANN.

[17]  A. Karr.  Random Graphs for Statistical Pattern Recognition , 2006 .

[18]  Christos Faloutsos,et al.  LOCI: fast outlier detection using the local correlation integral , 2003, Proceedings 19th International Conference on Data Engineering (Cat. No.03CH37405).